© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 674
    Prev
    Next
    INDEX
    Explanations

    quote marks followed by diverse words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    è´¨
    -0.09
    åĴ¦
    -0.08
    æĹ¥åIJİ
    -0.08
    åĽłä¸ºæĪij
    -0.08
     onLoad
    -0.08
    èĬĤèĥ½åĩıæİĴ
    -0.08
    Bridge
    -0.08
     either
    -0.08
    诸å¦Ĥ
    -0.08
    éī´
    -0.08
    POSITIVE LOGITS
    è¿Ļè¯Ŀ
    0.09
    éo
    0.09
     timing
    0.09
    å²Ķ
    0.08
    饱
    0.08
     Sith
    0.08
    aison
    0.08
    itech
    0.08
    æĥ¹
    0.08
    timing
    0.08
    Activations Density 0.220%

    No Known Activations